{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:SCK352MIW5P6WDGKNDAXQ4DVMY","short_pith_number":"pith:SCK352MI","canonical_record":{"source":{"id":"2005.01630","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-04T16:38:54Z","cross_cats_sorted":[],"title_canon_sha256":"962eafba2f339eed6a87448fa33b48757a6c1735f4694d751024fb6995d37c62","abstract_canon_sha256":"eaba93ba257145aa2730e018e0665d70fbba06909c67df8483c57536ca012aff"},"schema_version":"1.0"},"canonical_sha256":"9095bee988b75feb0cca68c17870756612279a77b05b2a3375387f7318ad29bd","source":{"kind":"arxiv","id":"2005.01630","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.01630","created_at":"2026-07-05T01:00:09Z"},{"alias_kind":"arxiv_version","alias_value":"2005.01630v1","created_at":"2026-07-05T01:00:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.01630","created_at":"2026-07-05T01:00:09Z"},{"alias_kind":"pith_short_12","alias_value":"SCK352MIW5P6","created_at":"2026-07-05T01:00:09Z"},{"alias_kind":"pith_short_16","alias_value":"SCK352MIW5P6WDGK","created_at":"2026-07-05T01:00:09Z"},{"alias_kind":"pith_short_8","alias_value":"SCK352MI","created_at":"2026-07-05T01:00:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:SCK352MIW5P6WDGKNDAXQ4DVMY","target":"record","payload":{"canonical_record":{"source":{"id":"2005.01630","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-04T16:38:54Z","cross_cats_sorted":[],"title_canon_sha256":"962eafba2f339eed6a87448fa33b48757a6c1735f4694d751024fb6995d37c62","abstract_canon_sha256":"eaba93ba257145aa2730e018e0665d70fbba06909c67df8483c57536ca012aff"},"schema_version":"1.0"},"canonical_sha256":"9095bee988b75feb0cca68c17870756612279a77b05b2a3375387f7318ad29bd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:00:09.672617Z","signature_b64":"F27PWgpows9A34fVUjdMI1I/jsef18G7DVLlk6dzABG7vJiYbLX/vlAVr1Aqr43rSRuBLXAWphJYEhqA91leDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9095bee988b75feb0cca68c17870756612279a77b05b2a3375387f7318ad29bd","last_reissued_at":"2026-07-05T01:00:09.672143Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:00:09.672143Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2005.01630","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:00:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3kcGJYXT07TwGraAgY4xt8X2ALQNFpqcB4x47mMwSj63WN5ACtVhtbOrsnEBG6d3zPfmfieb81d9xahTGLSDDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T05:39:39.135975Z"},"content_sha256":"666c34097720f3367e62082d3776651630508490fdb71b37751fd5b09e993f3e","schema_version":"1.0","event_id":"sha256:666c34097720f3367e62082d3776651630508490fdb71b37751fd5b09e993f3e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:SCK352MIW5P6WDGKNDAXQ4DVMY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Paradigm Discovery Problem","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexander Erdmann, Micha Elsner, Nizar Habash, Ryan Cotterell, Shijie Wu","submitted_at":"2020-05-04T16:38:54Z","abstract_excerpt":"This work treats the paradigm discovery problem (PDP), the task of learning an inflectional morphological system from unannotated sentences. We formalize the PDP and develop evaluation metrics for judging systems. Using currently available resources, we construct datasets for the task. We also devise a heuristic benchmark for the PDP and report empirical results on five diverse languages. Our benchmark system first makes use of word embeddings and string similarity to cluster forms by cell and by paradigm. Then, we bootstrap a neural transducer on top of the clustered data to predict words to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.01630","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2005.01630/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:00:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SsBfMGaJ7eSxRbKnoQQAh3muv0lVAI13pVifC4XZxNdppYVwngiHyiNv87zZHBZDEfHIT/pkmUdXdYi6YHF4Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T05:39:39.136766Z"},"content_sha256":"556f09137ad6fc859fae5dd225584127f42e35754f1809223772756bd98a6a80","schema_version":"1.0","event_id":"sha256:556f09137ad6fc859fae5dd225584127f42e35754f1809223772756bd98a6a80"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SCK352MIW5P6WDGKNDAXQ4DVMY/bundle.json","state_url":"https://pith.science/pith/SCK352MIW5P6WDGKNDAXQ4DVMY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SCK352MIW5P6WDGKNDAXQ4DVMY/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-07T05:39:39Z","links":{"resolver":"https://pith.science/pith/SCK352MIW5P6WDGKNDAXQ4DVMY","bundle":"https://pith.science/pith/SCK352MIW5P6WDGKNDAXQ4DVMY/bundle.json","state":"https://pith.science/pith/SCK352MIW5P6WDGKNDAXQ4DVMY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SCK352MIW5P6WDGKNDAXQ4DVMY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:SCK352MIW5P6WDGKNDAXQ4DVMY","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"eaba93ba257145aa2730e018e0665d70fbba06909c67df8483c57536ca012aff","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-04T16:38:54Z","title_canon_sha256":"962eafba2f339eed6a87448fa33b48757a6c1735f4694d751024fb6995d37c62"},"schema_version":"1.0","source":{"id":"2005.01630","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.01630","created_at":"2026-07-05T01:00:09Z"},{"alias_kind":"arxiv_version","alias_value":"2005.01630v1","created_at":"2026-07-05T01:00:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.01630","created_at":"2026-07-05T01:00:09Z"},{"alias_kind":"pith_short_12","alias_value":"SCK352MIW5P6","created_at":"2026-07-05T01:00:09Z"},{"alias_kind":"pith_short_16","alias_value":"SCK352MIW5P6WDGK","created_at":"2026-07-05T01:00:09Z"},{"alias_kind":"pith_short_8","alias_value":"SCK352MI","created_at":"2026-07-05T01:00:09Z"}],"graph_snapshots":[{"event_id":"sha256:556f09137ad6fc859fae5dd225584127f42e35754f1809223772756bd98a6a80","target":"graph","created_at":"2026-07-05T01:00:09Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2005.01630/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This work treats the paradigm discovery problem (PDP), the task of learning an inflectional morphological system from unannotated sentences. We formalize the PDP and develop evaluation metrics for judging systems. Using currently available resources, we construct datasets for the task. We also devise a heuristic benchmark for the PDP and report empirical results on five diverse languages. Our benchmark system first makes use of word embeddings and string similarity to cluster forms by cell and by paradigm. Then, we bootstrap a neural transducer on top of the clustered data to predict words to ","authors_text":"Alexander Erdmann, Micha Elsner, Nizar Habash, Ryan Cotterell, Shijie Wu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-04T16:38:54Z","title":"The Paradigm Discovery Problem"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.01630","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:666c34097720f3367e62082d3776651630508490fdb71b37751fd5b09e993f3e","target":"record","created_at":"2026-07-05T01:00:09Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"eaba93ba257145aa2730e018e0665d70fbba06909c67df8483c57536ca012aff","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-04T16:38:54Z","title_canon_sha256":"962eafba2f339eed6a87448fa33b48757a6c1735f4694d751024fb6995d37c62"},"schema_version":"1.0","source":{"id":"2005.01630","kind":"arxiv","version":1}},"canonical_sha256":"9095bee988b75feb0cca68c17870756612279a77b05b2a3375387f7318ad29bd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9095bee988b75feb0cca68c17870756612279a77b05b2a3375387f7318ad29bd","first_computed_at":"2026-07-05T01:00:09.672143Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:00:09.672143Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"F27PWgpows9A34fVUjdMI1I/jsef18G7DVLlk6dzABG7vJiYbLX/vlAVr1Aqr43rSRuBLXAWphJYEhqA91leDg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:00:09.672617Z","signed_message":"canonical_sha256_bytes"},"source_id":"2005.01630","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:666c34097720f3367e62082d3776651630508490fdb71b37751fd5b09e993f3e","sha256:556f09137ad6fc859fae5dd225584127f42e35754f1809223772756bd98a6a80"],"state_sha256":"f4feaeeaaa7bad5fbc754fed79e7540510c52f3ba0c0787a309540802f90db6f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"V1ER0bM43DeCSmdZqM73aa9TpPfMpMIFzRXhykwTczz6H6TR7xXXLUuNaBjBDwypsN+CBrmeAW2elBZXR4ojBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T05:39:39.142950Z","bundle_sha256":"a01fcac0879fe46e0bff69cc7f48f35e22b787366647961c24fd0e8b269a8a3e"}}